{"architectures": ["BertForMaskedLM"], "pad_token_id": 0, "gradient_checkpointing": false, "model_type": "bert", "vocab_size": 30522, "hidden_size": 768, "num_hidden_layers": 12, "num_attention_heads": 12, "hidden_act": "gelu", "intermediate_size": 3072, "hidden_dropout_prob": 0.1, "attention_probs_dropout_prob": 0.1, "max_position_embeddings": 512, "type_vocab_size": 2, "initializer_range": 0.02, "layer_norm_eps": 1e-12, "position_embedding_type": "absolute", "use_cache": true, "classifier_dropout": null, "neuron": {"model_class": "BertForSequenceClassification", "precision": "bfloat16", "num_neuron_cores_per_node": 2, "compiler_version": "2.12.68.0+4480452af", "tensor_parallel_size": 1, "pipeline_parallel_size": 1, "training": true, "input_specs": {"input_ids": [4, 256], "token_type_ids": [4, 256], "attention_mask": [4, 256], "labels": [4]}}}